From 4cacecaaa2bbf8af0967bd3eee43297fada475a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= Date: Sun, 10 Jan 2021 01:02:40 +0100 Subject: decodetree: Open files with encoding='utf-8' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When decodetree.py was added in commit 568ae7efae7, QEMU was using Python 2 which happily reads UTF-8 files in text mode. Python 3 requires either UTF-8 locale or an explicit encoding passed to open(). Now that Python 3 is required, explicit UTF-8 encoding for decodetree source files. To avoid further problems with the user locale, also explicit UTF-8 encoding for the generated C files. Explicit both input/output are plain text by using the 't' mode. This fixes: $ /usr/bin/python3 scripts/decodetree.py test.decode Traceback (most recent call last): File "scripts/decodetree.py", line 1397, in main() File "scripts/decodetree.py", line 1308, in main parse_file(f, toppat) File "scripts/decodetree.py", line 994, in parse_file for line in f: File "/usr/lib/python3.6/encodings/ascii.py", line 26, in decode return codecs.ascii_decode(input, self.errors)[0] UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 80: ordinal not in range(128) Reported-by: Peter Maydell Suggested-by: Yonggang Luo Reviewed-by: Eduardo Habkost Signed-off-by: Philippe Mathieu-Daudé Message-Id: <20210110000240.761122-1-f4bug@amsat.org> Signed-off-by: Richard Henderson --- scripts/decodetree.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'scripts') diff --git a/scripts/decodetree.py b/scripts/decodetree.py index 47aa9caf6d..4637b633e7 100644 --- a/scripts/decodetree.py +++ b/scripts/decodetree.py @@ -20,6 +20,7 @@ # See the syntax and semantics in docs/devel/decodetree.rst. # +import io import os import re import sys @@ -1304,7 +1305,7 @@ def main(): for filename in args: input_file = filename - f = open(filename, 'r') + f = open(filename, 'rt', encoding='utf-8') parse_file(f, toppat) f.close() @@ -1324,9 +1325,11 @@ def main(): prop_size(stree) if output_file: - output_fd = open(output_file, 'w') + output_fd = open(output_file, 'wt', encoding='utf-8') else: - output_fd = sys.stdout + output_fd = io.TextIOWrapper(sys.stdout.buffer, + encoding=sys.stdout.encoding, + errors="ignore") output_autogen() for n in sorted(arguments.keys()): -- cgit v1.2.3